Hugging Face's logo

Karayakar
/
akattsTokenizer

Model card Files
xet
Community
Karayakar commited on
Commit
34c1d53
·
verified ·
1 Parent(s): 7f98c0c

Upload 4 files

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +64 -0
  2. token_mapping.json +30 -0
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +118 -0
special_tokens_map.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<AUDIO_BOS>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<FRAME>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<spk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<lang:tr>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<lang:en>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<emo:neutral>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<emo:happy>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<emo:sad>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ }
59
+ ],
60
+ "bos_token": "<s>",
61
+ "eos_token": "<EOS>",
62
+ "pad_token": "<pad>",
63
+ "unk_token": "<unk>"
64
+ }
token_mapping.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "special_tokens": {
3
+ "audio_bos_token": "<AUDIO_BOS>",
4
+ "frame_token": "<FRAME>",
5
+ "eos_token": "<EOS>",
6
+ "speaker_token": "<spk>",
7
+ "lang_tokens": [
8
+ "<lang:tr>",
9
+ "<lang:en>"
10
+ ],
11
+ "emotion_tokens": [
12
+ "<emo:neutral>",
13
+ "<emo:happy>",
14
+ "<emo:sad>"
15
+ ],
16
+ "pad_token": "<pad>",
17
+ "unk_token": "<unk>",
18
+ "bos_token": "<s>"
19
+ },
20
+ "lang_to_id": {
21
+ "tr": 0,
22
+ "en": 1
23
+ },
24
+ "emotion_to_id": {
25
+ "neutral": 0,
26
+ "happy": 1,
27
+ "sad": 2
28
+ },
29
+ "audio_vocab_size": 4096
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,118 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<pad>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<unk>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<EOS>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<AUDIO_BOS>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "5": {
44
+ "content": "<FRAME>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "6": {
52
+ "content": "<spk>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "7": {
60
+ "content": "<lang:tr>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "8": {
68
+ "content": "<lang:en>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "9": {
76
+ "content": "<emo:neutral>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "10": {
84
+ "content": "<emo:happy>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "11": {
92
+ "content": "<emo:sad>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ }
99
+ },
100
+ "additional_special_tokens": [
101
+ "<AUDIO_BOS>",
102
+ "<FRAME>",
103
+ "<spk>",
104
+ "<lang:tr>",
105
+ "<lang:en>",
106
+ "<emo:neutral>",
107
+ "<emo:happy>",
108
+ "<emo:sad>"
109
+ ],
110
+ "bos_token": "<s>",
111
+ "clean_up_tokenization_spaces": false,
112
+ "eos_token": "<EOS>",
113
+ "extra_special_tokens": {},
114
+ "model_max_length": 1000000000000000019884624838656,
115
+ "pad_token": "<pad>",
116
+ "tokenizer_class": "PreTrainedTokenizer",
117
+ "unk_token": "<unk>"
118
+ }